Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The soft glow of the fairy lights illuminated the small garden, casting dancing shadows. Across the small table, Sophia was telling a story, her hands animated as she spoke. A gentle warmth filled him, a comfortable stillness in his chest.

"That ridiculous talent show we were in, right?" he started, smiling. "When your magic trick went horribly wrong?"

Sophia's expression lit up, a mixture of amusement and fondness. "Oh, my gosh, yes! The dove escaping and flying into the audience? Classic!"

He laughed, remembering the chaos. “I recall the dove. But I especially remember how much fun we had creating it.”

Sophia chuckled and leaned closer to him.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

This story is one of 1,000 stories generated for the emotion loving. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 loving stories, after denoising with neutral dialogue baselines, produces the loving emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the loving vector is projected through the unembedding matrix.

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417